Author's Description
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Z.ai's GLM 4.5V demonstrates moderate speed performance, ranking in the 34th percentile, and offers moderate pricing, placing it in the 29th percentile across benchmarks. A standout feature is its exceptional reliability, boasting a 98% success rate, indicating minimal technical failures. The model exhibits strong performance in several key areas. It achieves high accuracy in Email Classification (99%), Reasoning (92%), and Coding (92%), suggesting proficiency in structured data processing, logical problem-solving, and programming tasks. Its General Knowledge is also impressive at 99%. However, a significant weakness is observed in Instruction Following, where it scores a low 5.1% accuracy, indicating challenges with complex multi-step directives. Hallucination rates are relatively low at 92% accuracy, showing a good ability to acknowledge uncertainty. Mathematics performance is moderate at 85%. The hybrid inference mode, with its "thinking" and "non-thinking" options, offers flexibility for different application needs, particularly for multimodal agent applications where deep reasoning or fast responses are critical.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.6 |
| Completion | $1.8 |
| Input Cache Read | $0.11 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Z.AI
|
Z.AI | z-ai/glm-4.5v | 65K | $0.6 / 1M tokens | $1.8 / 1M tokens |
|
Novita
|
Novita | z-ai/glm-4.5v | 65K | $0.6 / 1M tokens | $1.8 / 1M tokens |
|
Parasail
|
Parasail | z-ai/glm-4.5v | 65K | $0.6 / 1M tokens | $1.8 / 1M tokens |
|
DeepInfra
|
DeepInfra | z-ai/glm-4.5v | 65K | $0.6 / 1M tokens | $1.8 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by z-ai
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Z.ai: GLM 5.1 | Apr 07, 2026 | — | 202K |
Text input
Text output
|
★ | ★★★★★ | $$$$$ |
| Z.ai: GLM 5V Turbo | Apr 01, 2026 | — | 202K |
Video input
Text input
Image input
Text output
|
★★ | ★★★★ | $$$$$ |
| Z.ai: GLM 5 Turbo Unavailable | Mar 15, 2026 | — | 202K |
Text input
Text output
|
— | — | $$$$$ |
| Z.ai: GLM 5 Turbo | Mar 15, 2026 | — | 202K |
Text input
Text output
|
★★ | ★★★★★ | $$$$$ |
| Z.ai: GLM 5 | Feb 11, 2026 | — | 202K |
Text input
Text output
|
★ | ★★★★ | $$$$$ |
| Z.ai: GLM 5 Unavailable | Feb 11, 2026 | — | 204K |
Text input
Text output
|
★ | ★★★★ | $ |
| Z.ai: GLM 4.7 Flash | Jan 19, 2026 | ~30B | 202K |
Text input
Text output
|
★ | ★★★ | $$$$ |
| Z.ai: GLM 4.7 | Dec 21, 2025 | — | 202K |
Text input
Text output
|
★ | ★★★★ | $$$$$ |
| Z.ai: GLM 4.6V | Dec 08, 2025 | — | 131K |
Video input
Text input
Image input
Text output
|
★★ | ★★★★★ | $$$$ |
| Z.ai: GLM 4.6 | Sep 30, 2025 | — | 202K |
Text input
Text output
|
★ | ★★★ | $$$$$ |
| Z.ai: GLM 4.6 (exacto) Unavailable | Sep 30, 2025 | — | 202K |
Text input
Text output
|
— | — | $$$$ |
| Z.ai: GLM 4.5 | Jul 25, 2025 | — | 131K |
Text input
Text output
|
★ | ★★★★ | $$$$$ |
| Z.ai: GLM 4.5 Air | Jul 25, 2025 | — | 131K |
Text input
Text output
|
★ | ★★ | $$$$ |
| Z.ai: GLM 4 32B | Jul 24, 2025 | 32B | 128K |
Text input
Text output
|
★★★ | ★ | $$ |